Merge branch 'main' of github.com:alibaba-damo-academy/FunASR

add

README.md

@@ -144,7 +144,7 @@ for i in range(total_chunk_num):
 ```
 Note: `chunk_size` is the configuration for streaming latency.` [0,10,5]` indicates that the real-time display granularity is `10*60=600ms`, and the lookahead information is `5*60=300ms`. Each inference input is `600ms` (sample points are `16000*0.6=960`), and the output is the corresponding text. For the last speech segment input, `is_final=True` needs to be set to force the output of the last word.
 
-### Voice Activity Detection (streaming)
+### Voice Activity Detection (Non-Streaming)
 ```python
 from funasr import AutoModel
 
@@ -153,7 +153,7 @@ wav_file = f"{model.model_path}/example/asr_example.wav"
 res = model.generate(input=wav_file)
 print(res)
 ```
-### Voice Activity Detection (Non-streaming)
+### Voice Activity Detection (Streaming)
 ```python
 from funasr import AutoModel
 

examples/industrial_data_pretraining/seaco_paraformer/demo.py

@@ -17,6 +17,6 @@ model = AutoModel(model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-com
 
 res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
                      hotword='达摩院 魔搭',
-                     # sentence_timestamp=True,
+                     # sentence_timestamp=True,  # return sentence level information when spk_model is not given
                     )
 print(res)

funasr/models/campplus/utils.py

@@ -212,7 +212,7 @@ def distribute_spk(sentence_list, sd_time_list):
             if overlap > max_overlap:
                 max_overlap = overlap
                 sentence_spk = spk
-        d['spk'] = sentence_spk
+        d['spk'] = int(sentence_spk)
         sd_sentence_list.append(d)
     return sd_sentence_list